diff options
Diffstat (limited to 'drivers/cxl/cxlmem.h')
| -rw-r--r-- | drivers/cxl/cxlmem.h | 199 |
1 files changed, 127 insertions, 72 deletions
diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index af8169ccdbc0..434031a0c1f7 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -3,11 +3,12 @@ #ifndef __CXL_MEM_H__ #define __CXL_MEM_H__ #include <uapi/linux/cxl_mem.h> +#include <linux/pci.h> #include <linux/cdev.h> #include <linux/uuid.h> -#include <linux/rcuwait.h> -#include <linux/cxl-event.h> #include <linux/node.h> +#include <cxl/event.h> +#include <cxl/mailbox.h> #include "cxl.h" /* CXL 2.0 8.2.8.5.1.1 Memory Device Status Register */ @@ -44,6 +45,11 @@ * @endpoint: connection to the CXL port topology for this memory device * @id: id number of this memdev instance. * @depth: endpoint port depth + * @scrub_cycle: current scrub cycle set for this device + * @scrub_region_id: id number of a backed region (if any) for which current scrub cycle set + * @err_rec_array: List of xarrarys to store the memdev error records to + * check attributes for a memory repair operation are from + * current boot. */ struct cxl_memdev { struct device dev; @@ -55,6 +61,9 @@ struct cxl_memdev { struct cxl_port *endpoint; int id; int depth; + u8 scrub_cycle; + int scrub_region_id; + void *err_rec_array; }; static inline struct cxl_memdev *to_cxl_memdev(struct device *dev) @@ -96,6 +105,19 @@ int devm_cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled, resource_size_t base, resource_size_t len, resource_size_t skipped); +#define CXL_NR_PARTITIONS_MAX 2 + +struct cxl_dpa_info { + u64 size; + struct cxl_dpa_part_info { + struct range range; + enum cxl_partition_mode mode; + } part[CXL_NR_PARTITIONS_MAX]; + int nr_partitions; +}; + +int cxl_dpa_setup(struct cxl_dev_state *cxlds, const struct cxl_dpa_info *info); + static inline struct cxl_ep *cxl_ep_load(struct cxl_port *port, struct cxl_memdev *cxlmd) { @@ -105,42 +127,6 @@ static inline struct cxl_ep *cxl_ep_load(struct cxl_port *port, return xa_load(&port->endpoints, (unsigned long)&cxlmd->dev); } -/** - * struct cxl_mbox_cmd - A command to be submitted to hardware. - * @opcode: (input) The command set and command submitted to hardware. - * @payload_in: (input) Pointer to the input payload. - * @payload_out: (output) Pointer to the output payload. Must be allocated by - * the caller. - * @size_in: (input) Number of bytes to load from @payload_in. - * @size_out: (input) Max number of bytes loaded into @payload_out. - * (output) Number of bytes generated by the device. For fixed size - * outputs commands this is always expected to be deterministic. For - * variable sized output commands, it tells the exact number of bytes - * written. - * @min_out: (input) internal command output payload size validation - * @poll_count: (input) Number of timeouts to attempt. - * @poll_interval_ms: (input) Time between mailbox background command polling - * interval timeouts. - * @return_code: (output) Error code returned from hardware. - * - * This is the primary mechanism used to send commands to the hardware. - * All the fields except @payload_* correspond exactly to the fields described in - * Command Register section of the CXL 2.0 8.2.8.4.5. @payload_in and - * @payload_out are written to, and read from the Command Payload Registers - * defined in CXL 2.0 8.2.8.4.8. - */ -struct cxl_mbox_cmd { - u16 opcode; - void *payload_in; - void *payload_out; - size_t size_in; - size_t size_out; - size_t min_out; - int poll_count; - int poll_interval_ms; - u16 return_code; -}; - /* * Per CXL 3.0 Section 8.2.8.4.5.1 */ @@ -161,7 +147,7 @@ struct cxl_mbox_cmd { C(FWRESET, -ENXIO, "FW failed to activate, needs cold reset"), \ C(HANDLE, -ENXIO, "one or more Event Record Handles were invalid"), \ C(PADDR, -EFAULT, "physical address specified is invalid"), \ - C(POISONLMT, -ENXIO, "poison injection limit has been reached"), \ + C(POISONLMT, -EBUSY, "poison injection limit has been reached"), \ C(MEDIAFAILURE, -ENXIO, "permanent issue with the media"), \ C(ABORT, -ENXIO, "background cmd was aborted by device"), \ C(SECURITY, -ENXIO, "not valid in the current security state"), \ @@ -268,7 +254,7 @@ enum security_cmd_enabled_bits { * @max_errors: Maximum media error records held in device cache * @enabled_cmds: All poison commands enabled in the CEL * @list_out: The poison list payload returned by device - * @lock: Protect reads of the poison list + * @mutex: Protect reads of the poison list * * Reads of the poison list are synchronized to ensure that a reader * does not get an incomplete list because their request overlapped @@ -279,7 +265,7 @@ struct cxl_poison_state { u32 max_errors; DECLARE_BITMAP(enabled_cmds, CXL_POISON_ENABLED_MAX); struct cxl_mbox_poison_out *list_out; - struct mutex lock; /* Protect reads of poison list */ + struct mutex mutex; /* Protect reads of poison list */ }; /* @@ -397,15 +383,29 @@ enum cxl_devtype { * struct cxl_dpa_perf - DPA performance property entry * @dpa_range: range for DPA address * @coord: QoS performance data (i.e. latency, bandwidth) + * @cdat_coord: raw QoS performance data from CDAT * @qos_class: QoS Class cookies */ struct cxl_dpa_perf { struct range dpa_range; struct access_coordinate coord[ACCESS_COORDINATE_MAX]; + struct access_coordinate cdat_coord[ACCESS_COORDINATE_MAX]; int qos_class; }; /** + * struct cxl_dpa_partition - DPA partition descriptor + * @res: shortcut to the partition in the DPA resource tree (cxlds->dpa_res) + * @perf: performance attributes of the partition from CDAT + * @mode: operation mode for the DPA capacity, e.g. ram, pmem, dynamic... + */ +struct cxl_dpa_partition { + struct resource res; + struct cxl_dpa_perf perf; + enum cxl_partition_mode mode; +}; + +/** * struct cxl_dev_state - The driver device state * * cxl_dev_state represents the CXL driver/device state. It provides an @@ -420,10 +420,12 @@ struct cxl_dpa_perf { * @rcd: operating in RCD mode (CXL 3.0 9.11.8 CXL Devices Attached to an RCH) * @media_ready: Indicate whether the device media is usable * @dpa_res: Overall DPA resource tree for the device - * @pmem_res: Active Persistent memory capacity configuration - * @ram_res: Active Volatile memory capacity configuration + * @part: DPA partition array + * @nr_partitions: Number of DPA partitions * @serial: PCIe Device Serial Number * @type: Generic Memory Class device or Vendor Specific Memory device + * @cxl_mbox: CXL mailbox context + * @cxlfs: CXL features context */ struct cxl_dev_state { struct device *dev; @@ -434,12 +436,33 @@ struct cxl_dev_state { bool rcd; bool media_ready; struct resource dpa_res; - struct resource pmem_res; - struct resource ram_res; + struct cxl_dpa_partition part[CXL_NR_PARTITIONS_MAX]; + unsigned int nr_partitions; u64 serial; enum cxl_devtype type; + struct cxl_mailbox cxl_mbox; +#ifdef CONFIG_CXL_FEATURES + struct cxl_features_state *cxlfs; +#endif }; +static inline resource_size_t cxl_pmem_size(struct cxl_dev_state *cxlds) +{ + /* + * Static PMEM may be at partition index 0 when there is no static RAM + * capacity. + */ + for (int i = 0; i < cxlds->nr_partitions; i++) + if (cxlds->part[i].mode == CXL_PARTMODE_PMEM) + return resource_size(&cxlds->part[i].res); + return 0; +} + +static inline struct cxl_dev_state *mbox_to_cxlds(struct cxl_mailbox *cxl_mbox) +{ + return dev_get_drvdata(cxl_mbox->host); +} + /** * struct cxl_memdev_state - Generic Type-3 Memory Device Class driver data * @@ -448,62 +471,40 @@ struct cxl_dev_state { * the functionality related to that like Identify Memory Device and Get * Partition Info * @cxlds: Core driver state common across Type-2 and Type-3 devices - * @payload_size: Size of space for payload - * (CXL 2.0 8.2.8.4.3 Mailbox Capabilities Register) * @lsa_size: Size of Label Storage Area * (CXL 2.0 8.2.9.5.1.1 Identify Memory Device) - * @mbox_mutex: Mutex to synchronize mailbox access. * @firmware_version: Firmware version for the memory device. - * @enabled_cmds: Hardware commands found enabled in CEL. - * @exclusive_cmds: Commands that are kernel-internal only * @total_bytes: sum of all possible capacities * @volatile_only_bytes: hard volatile capacity * @persistent_only_bytes: hard persistent capacity * @partition_align_bytes: alignment size for partition-able capacity * @active_volatile_bytes: sum of hard + soft volatile * @active_persistent_bytes: sum of hard + soft persistent - * @next_volatile_bytes: volatile capacity change pending device reset - * @next_persistent_bytes: persistent capacity change pending device reset - * @ram_perf: performance data entry matched to RAM partition - * @pmem_perf: performance data entry matched to PMEM partition * @event: event log driver state * @poison: poison driver state info * @security: security driver state info * @fw: firmware upload / activation state - * @mbox_wait: RCU wait for mbox send completely - * @mbox_send: @dev specific transport for transmitting mailbox commands + * @mce_notifier: MCE notifier * * See CXL 3.0 8.2.9.8.2 Capacity Configuration and Label Storage for * details on capacity parameters. */ struct cxl_memdev_state { struct cxl_dev_state cxlds; - size_t payload_size; size_t lsa_size; - struct mutex mbox_mutex; /* Protects device mailbox and firmware */ char firmware_version[0x10]; - DECLARE_BITMAP(enabled_cmds, CXL_MEM_COMMAND_ID_MAX); - DECLARE_BITMAP(exclusive_cmds, CXL_MEM_COMMAND_ID_MAX); u64 total_bytes; u64 volatile_only_bytes; u64 persistent_only_bytes; u64 partition_align_bytes; u64 active_volatile_bytes; u64 active_persistent_bytes; - u64 next_volatile_bytes; - u64 next_persistent_bytes; - - struct cxl_dpa_perf ram_perf; - struct cxl_dpa_perf pmem_perf; struct cxl_event_state event; struct cxl_poison_state poison; struct cxl_security_state security; struct cxl_fw_state fw; - - struct rcuwait mbox_wait; - int (*mbox_send)(struct cxl_memdev_state *mds, - struct cxl_mbox_cmd *cmd); + struct notifier_block mce_notifier; }; static inline struct cxl_memdev_state * @@ -531,6 +532,10 @@ enum cxl_opcode { CXL_MBOX_OP_GET_LOG_CAPS = 0x0402, CXL_MBOX_OP_CLEAR_LOG = 0x0403, CXL_MBOX_OP_GET_SUP_LOG_SUBLIST = 0x0405, + CXL_MBOX_OP_GET_SUPPORTED_FEATURES = 0x0500, + CXL_MBOX_OP_GET_FEATURE = 0x0501, + CXL_MBOX_OP_SET_FEATURE = 0x0502, + CXL_MBOX_OP_DO_MAINTENANCE = 0x0600, CXL_MBOX_OP_IDENTIFY = 0x4000, CXL_MBOX_OP_GET_PARTITION_INFO = 0x4100, CXL_MBOX_OP_SET_PARTITION_INFO = 0x4101, @@ -563,7 +568,7 @@ enum cxl_opcode { 0x3b, 0x3f, 0x17) #define DEFINE_CXL_VENDOR_DEBUG_UUID \ - UUID_INIT(0xe1819d9, 0x11a9, 0x400c, 0x81, 0x1f, 0xd6, 0x07, 0x19, \ + UUID_INIT(0x5e1819d9, 0x11a9, 0x400c, 0x81, 0x1f, 0xd6, 0x07, 0x19, \ 0x40, 0x3d, 0x86) struct cxl_mbox_get_supported_logs { @@ -629,6 +634,14 @@ struct cxl_mbox_identify { 0x13, 0xb7, 0x74) /* + * Memory Sparing Event Record UUID + * CXL rev 3.2 section 8.2.10.2.1.4: Table 8-60 + */ +#define CXL_EVENT_MEM_SPARING_UUID \ + UUID_INIT(0xe71f3a40, 0x2d29, 0x4092, 0x8a, 0x39, 0x4d, 0x1c, 0x96, \ + 0x6c, 0x7c, 0x65) + +/* * Get Event Records output payload * CXL rev 3.0 section 8.2.9.2.2; Table 8-50 */ @@ -694,6 +707,23 @@ struct cxl_mbox_set_partition_info { #define CXL_SET_PARTITION_IMMEDIATE_FLAG BIT(0) +/* Get Health Info Output Payload CXL 3.2 Spec 8.2.10.9.3.1 Table 8-148 */ +struct cxl_mbox_get_health_info_out { + u8 health_status; + u8 media_status; + u8 additional_status; + u8 life_used; + __le16 device_temperature; + __le32 dirty_shutdown_cnt; + __le32 corrected_volatile_error_cnt; + __le32 corrected_persistent_error_cnt; +} __packed; + +/* Set Shutdown State Input Payload CXL 3.2 Spec 8.2.10.9.3.5 Table 8-152 */ +struct cxl_mbox_set_shutdown_state_in { + u8 state; +} __packed; + /* Set Timestamp CXL 3.0 Spec 8.2.9.4.2 */ struct cxl_mbox_set_timestamp_in { __le64 timestamp; @@ -814,12 +844,12 @@ enum { CXL_PMEM_SEC_PASS_USER, }; -int cxl_internal_send_cmd(struct cxl_memdev_state *mds, +int cxl_internal_send_cmd(struct cxl_mailbox *cxl_mbox, struct cxl_mbox_cmd *cmd); int cxl_dev_state_identify(struct cxl_memdev_state *mds); int cxl_await_media_ready(struct cxl_dev_state *cxlds); int cxl_enumerate_cmds(struct cxl_memdev_state *mds); -int cxl_mem_create_range_info(struct cxl_memdev_state *mds); +int cxl_mem_dpa_fetch(struct cxl_memdev_state *mds, struct cxl_dpa_info *info); struct cxl_memdev_state *cxl_memdev_state_create(struct device *dev); void set_exclusive_cxl_commands(struct cxl_memdev_state *mds, unsigned long *cmds); @@ -830,6 +860,8 @@ void cxl_event_trace_record(const struct cxl_memdev *cxlmd, enum cxl_event_log_type type, enum cxl_event_type event_type, const uuid_t *uuid, union cxl_event *evt); +int cxl_get_dirty_count(struct cxl_memdev_state *mds, u32 *count); +int cxl_arm_dirty_shutdown(struct cxl_memdev_state *mds); int cxl_set_timestamp(struct cxl_memdev_state *mds); int cxl_poison_state_init(struct cxl_memdev_state *mds); int cxl_mem_get_poison(struct cxl_memdev *cxlmd, u64 offset, u64 len, @@ -837,6 +869,29 @@ int cxl_mem_get_poison(struct cxl_memdev *cxlmd, u64 offset, u64 len, int cxl_trigger_poison_list(struct cxl_memdev *cxlmd); int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa); int cxl_clear_poison(struct cxl_memdev *cxlmd, u64 dpa); +int cxl_inject_poison_locked(struct cxl_memdev *cxlmd, u64 dpa); +int cxl_clear_poison_locked(struct cxl_memdev *cxlmd, u64 dpa); + +#ifdef CONFIG_CXL_EDAC_MEM_FEATURES +int devm_cxl_memdev_edac_register(struct cxl_memdev *cxlmd); +int devm_cxl_region_edac_register(struct cxl_region *cxlr); +int cxl_store_rec_gen_media(struct cxl_memdev *cxlmd, union cxl_event *evt); +int cxl_store_rec_dram(struct cxl_memdev *cxlmd, union cxl_event *evt); +void devm_cxl_memdev_edac_release(struct cxl_memdev *cxlmd); +#else +static inline int devm_cxl_memdev_edac_register(struct cxl_memdev *cxlmd) +{ return 0; } +static inline int devm_cxl_region_edac_register(struct cxl_region *cxlr) +{ return 0; } +static inline int cxl_store_rec_gen_media(struct cxl_memdev *cxlmd, + union cxl_event *evt) +{ return 0; } +static inline int cxl_store_rec_dram(struct cxl_memdev *cxlmd, + union cxl_event *evt) +{ return 0; } +static inline void devm_cxl_memdev_edac_release(struct cxl_memdev *cxlmd) +{ return; } +#endif #ifdef CONFIG_CXL_SUSPEND void cxl_mem_active_inc(void); |
